Summary
And in Conclusion
Textbook Readings
P&H 1.7, 1.8, 2.11, 4.10, 4.11, 5.10, 6.1-6.3, 6.5, 6.7
Additional References
dgemm matrix multiplication references in P&H, 2nd edition:
- Section 1.10: 2-D Python code (no figure; embedded in text)
- Figure 2.43: Naive C code
- Figure 3.19: Intel intrinsics, AVX512 (the actual Figure 3.22)
- Figure 3.22: (does not exist but is referenced by several figures)
- Figure 4.78: (does not exist but is referenced by several figures)
- Figure 4.82: Loop Unrolling (the actual Figure 4.78)
- Figure 5.21: Cache Blocking
- Figure 5.48: Cache Blocking + Loop Unrolling
- Figure 6.31: OpenMP
If you’re curious about numpy:
Exercises
Check your knowledge!